A decentralized optimization approach employing cooperative cycle-regulation in an intersection-centric manner: A complex urban simulative case study

Abstract The upcoming high population density rise in metropolitan areas is anticipated to further deteriorate the traffic conditions. To tackle this problem, advanced ICT applications have been employed, able to monitor and manage traffic in real time. In practice, to efficiently correspond to dynamic traffic conditions those applications require to be frequently reconfigured – an operation that usually involves expert-teams manually adjusting the traffic-regulating strategies regularly. However, these manual procedures are not adequately aligned with the traffic situation since complicated stochastic dynamics, model unavailability and data inner-transmission constraints usually emerge. In order to overcome such cumbersome and expensive adjustment procedures modern decentralized adaptive optimization is widely accepted and recognized as an efficient automated solution for tuning the control strategy on-the-fly. Motivated by the above, L4GCAO, a decentralized, model independent, flexible optimization technique has been designed for optimizing cycle management at a local level to improve network performance at the global level, by automatically adjusting the cycle-regulating parameters in an intersection-centric manner, through cooperating self-learning agents. This paper studies L4GCAO's first application on a realistic traffic-network simulation scheme that examines the online fine-tuning process of the cycle-regulating parameters. Moreover, in order to evaluate the decentralized L4GCAO performance, two levels of performance benchmarking have been considered: a comparison with CAO - its well-established centralized counterpart; an already well-designed fixed-time management plan. In all cases, L4GCAO exhibits an almost equivalent performance improvement compared to CAO, both with respect to a properly fixed-time traffic management plan, while utilizes less parameters in a non-centralized manner.

[1]  Chris Manzie,et al.  Enhancing the performance of existing urban traffic light control through extremum-seeking , 2016 .

[2]  Martin Guay,et al.  Distributed extremum-seeking control over networks of dynamic agents , 2015, 2015 American Control Conference (ACC).

[3]  Iakovos Michailidis,et al.  Model-based and model-free “plug-and-play” building energy efficient control , 2015 .

[4]  Elias B. Kosmatopoulos,et al.  An adaptive optimization scheme with satisfactory transient performance , 2009, Autom..

[5]  Miroslav Krstic,et al.  Stability of extremum seeking feedback for general nonlinear dynamic systems , 2000, Autom..

[6]  Iakovos Michailidis,et al.  Local4Global Adaptive Optimization and control for System-of-Systems , 2015, 2015 European Control Conference (ECC).

[7]  Denis Dochain,et al.  Adaptive extremum seeking control of continuous stirred tank bioreactors with unknown growth kinetics , 2004, Autom..

[8]  Pravin Varaiya,et al.  Max pressure control of a network of signalized intersections , 2013 .

[9]  Iakovos Michailidis,et al.  A “plug-n-play” computationally efficient approach for control design of large-scale nonlinear systems using co-simulation , 2013, 52nd IEEE Conference on Decision and Control.

[10]  R H Smith,et al.  NETWORKWIDE APPROACH TO OPTIMAL SIGNAL TIMING FOR INTEGRATED TRANSIT VEHICLE AND TRAFFIC OPERATIONS , 1997 .

[11]  U. Ozguner,et al.  Nash solution by extremum seeking control approach , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[12]  Markos Papageorgiou,et al.  Application and Evaluation of the Signal Traffic Control Strategy TUC in Chania , 2005, J. Intell. Transp. Syst..

[13]  D. Gargett,et al.  Traffic growth in Australian cities: causes, prevention and cure , 2004 .

[14]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[15]  J L Ferrer,et al.  ANALYSIS OF DYNAMIC VEHICLE GUIDANCE SYSTEMS BY MICROSIMULATION WITH AIMSUN2 , 1999 .

[16]  Yu. M. Ermol’ev.  On the method of generalized stochastic gradients and quasi-Féjer sequences , 1969 .

[17]  Tao Yao,et al.  Data-driven linear decision rule approach for distributionally robust optimization of on-line signal control , 2015 .

[18]  Rita Streblow,et al.  Simulation-based implementation and evaluation of a system of systems optimization algorithm in a building control system , 2016, 2016 24th Mediterranean Conference on Control and Automation (MED).

[19]  Markos Papageorgiou,et al.  Automated tuning of ITS management and control systems: Results from real-life experiments , 2016 .

[20]  Ali Hajbabaie,et al.  A Cell‐Based Distributed‐Coordinated Approach for Network‐Level Signal Timing Optimization , 2017, Comput. Aided Civ. Infrastructure Eng..

[21]  Elias B. Kosmatopoulos,et al.  Large Scale Nonlinear Control System Fine-Tuning Through Learning , 2009, IEEE Transactions on Neural Networks.

[22]  Jeffrey Kenworthy,et al.  Trends in Vehicle Kilometres of Travel in World Cities, 1960-1990: Underlying Drivers and Policy Responses. , 2004 .

[23]  P R Lowrie,et al.  The Sydney coordinated adaptive traffic system - principles, methodology, algorithms , 1982 .

[24]  Mike Smith,et al.  Traffic signal control and route choice: A new assignment and control model which designs signal timings , 2015 .

[25]  Elias B. Kosmatopoulos,et al.  Autonomous Self-Regulating Intersections in Large-Scale Urban Traffic Networks: a Chania City Case Study , 2018, 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT).

[26]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[27]  Leandros Tassiulas,et al.  Stability properties of constrained queueing systems and scheduling policies for maximum throughput in multihop radio networks , 1992 .

[28]  Feng Zhu,et al.  Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility , 2018, J. Intell. Transp. Syst..

[29]  Ying Tan,et al.  On non-local stability properties of extremum seeking control , 2006, Autom..

[30]  Markos Papageorgiou,et al.  Adaptive Fine-Tuning of Nonlinear Control Systems With Application to the Urban Traffic Control Strategy TUC , 2007, IEEE Transactions on Control Systems Technology.

[31]  Nan Xiao,et al.  Throughput optimality of extended back-pressure traffic signal control algorithm , 2015, 2015 23rd Mediterranean Conference on Control and Automation (MED).

[32]  P. Newman,et al.  ‘Peak Car Use’: Understanding the Demise of Automobile Dependence , 2011 .

[33]  Tianshu Chu,et al.  Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control , 2019, IEEE Transactions on Intelligent Transportation Systems.

[34]  Michael Q. Wang,et al.  Vehicle-use intensity in China: Current status and future trend , 2012 .

[35]  Jie Wang,et al.  Large-scale traffic grid signal control with regional Reinforcement Learning , 2016, 2016 American Control Conference (ACC).

[36]  Markos Papageorgiou,et al.  Extensions and New Applications of the Traffic-Responsive Urban Control Strategy: Coordinated Signal Control for Urban Networks , 2003 .

[37]  Milos S. Stankovic,et al.  Decentralized Parameter Estimation by Consensus Based Stochastic Approximation , 2011, IEEE Trans. Autom. Control..

[38]  Martin Guay,et al.  Parameter convergence in adaptive extremum-seeking control , 2007, Autom..

[39]  M. Ben-Akiva,et al.  An enhanced SPSA algorithm for the calibration of Dynamic Traffic Assignment models , 2015 .

[40]  Fei-Yue Wang,et al.  Agent-Based Control for Networked Traffic Management Systems , 2005, IEEE Intell. Syst..

[41]  Markos Papageorgiou,et al.  Simulation-based synthesis for approximately optimal urban traffic light management , 2015, 2015 American Control Conference (ACC).

[42]  Jie Wang,et al.  Traffic signal control by distributed Reinforcement Learning with min-sum communication , 2017, 2017 American Control Conference (ACC).

[43]  Markos Papageorgiou,et al.  Adaptive Performance Optimization for Large-Scale Traffic Control Systems , 2011, IEEE Transactions on Intelligent Transportation Systems.

[44]  J. Spall.  Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[45]  Iakovos Michailidis,et al.  A "plug and play" computationally efficient approach for control design of large-scale nonlinear systems using cosimulation: a combination of two "ingredients" , 2014, IEEE Control Systems.